© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114157
    Prev
    Next
    INDEX
    Explanations

    built up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elic
    -0.09
     Ged
    -0.09
     Het
    -0.09
     Cow
    -0.08
    poss
    -0.08
    utow
    -0.08
     Forums
    -0.08
    fg
    -0.08
     jaws
    -0.08
    aken
    -0.08
    POSITIVE LOGITS
     momentum
    0.17
     rapport
    0.15
     clientele
    0.13
     courage
    0.13
     Momentum
    0.13
     thirst
    0.12
     sweat
    0.12
     sizable
    0.12
     enough
    0.11
     backlog
    0.11
    Activations Density 0.044%

    No Known Activations